Data Scientist - Supply Chain

Context

The team is looking for a new Data Scientist based in Lille or Paris.

The team, part of the Data Supply Chain, is responsible for the design, development, and maintenance of innovative analytical and Artificial Intelligence solutions around supply chain use cases such as multi-echelon demand forecasting, target stock estimation, or shortage management, to name a few. You will work within a multidisciplinary team composed of Data Scientists, Data Analysts, Analytics Engineers, and ML Engineers, working in an agile manner and in close proximity with Product and Engineering contacts as well as business users.

Missions

Your Mission: Analyse, Develop and Deploy Inventory Optimization solutions at scale

As a Data Scientist, you will play a pivotal role in bridging the gap between business strategy and high-quality technical implementation within the Inventory Optimization team. Your mission is to develop and deploy production-grade ML models for demand forecasting across BTB and BTC channels on different geographical granularities (stores, warehouses), directly contributing to stock management optimization. You will work on building robust models, collaborating with a multidisciplinary team of data experts, and partnering with Product and Business stakeholders to translate business requirements into scalable, reliable reality.

Your Responsibilities

• Advanced Data Science

  • Strategic Data Analytics: Conduct in-depth diagnostic analyses of production forecasts and user-driven overrides. Leverage these insights to identify patterns, refine model accuracy, accelerate deployment cycles, and drive automation initiatives.

  • Impactful Modeling: Develop advanced statistical and ML algorithms that integrate internal variables (price, assortment) with external signals (weather, calendar data, market trends) for global replenishment.

  • End-to-End Lifecycle: Manage the end-to-end lifecycle of your ML solutions—from R&D to CI/CD deployment—ensuring the stability and efficiency of the forecasting engine.

  • Communication: Translate complex data insights into actionable recommendations for Supply Chain and Business stakeholders through compelling visualization and storytelling.

• Team Collaboration

  • Technical Contribution: Participate actively in daily technical initiatives, contributing to codebases, removing blockers, and maintaining high velocity within the team.

  • Peer Review & Quality: Participate in code and model review processes, promoting best practices for ML engineering, reproducibility, and documentation.

  • Growth: Actively collaborate with team members, contributing to a culture of technical excellence and sharing knowledge to solve complex problems.

Tools & Environment

• Execution Engine: Databricks, AWS, GCP

• Payload: Python, Spark, Scikit-Learn, Tensorflow / Pytorch, Pyspark

• CICD: Github Actions

• Serving: Docker, Protobuf, gRPC

• Model registry, Model Tracking: MLFlow

• Orchestration: Airflow

• Documentation / code: Git, Confluence

• Data Visualisation: Tableau

Working Conditions

• Location: Lille

• Daily rate: 600€

1. Good knowledge of Time Series forecasting with successful experience working on ML pipelines in production at scale
2. Experience working in collaborative technical teams with strong ability to give and receive constructive feedback
3. Understanding of supply chain concepts, particularly stock optimization and demand forecasting
4. Ability to transform business needs into well-defined technical problems
5. Ability to clearly explain model predictions to non-technical stakeholders and discuss gradient boosting hyperparameters with engineers
6. Balance between state-of-the-art research and delivering reliable, maintainable code
7. Professional command of English
8. Expertise in Machine Learning and Python programming
9. Advanced knowledge of Databricks and dbt
10. Confirmed skills in Supply Chain and Time Series forecasting